A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Filters
Demonyms and Compound Relational Nouns in Nominal Open IE
2016
Proceedings of the 5th Workshop on Automated Knowledge Base Construction
Preserved Fulltext
We substantially improve the quality of Open IE from compound noun phrases by focusing on phenomena like demonyms and compound relational nouns. ...
Extracting open relational tuples that are mediated by nouns (instead of verbs) is important since titles and entity attributes are often expressed nominally. ...
We thank Michael Schmitz, the author of the original RELNOUN system, for helping with details of the algorithm. ...
doi:10.18653/v1/w16-1307
dblp:conf/akbc/PalM16
fatcat:kohdtpich5axbeujzupznmh4hu
ZORE: A Syntax-based System for Chinese Open Relation Extraction
2014
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Open Relation Extraction (ORE) overcomes the limitations of traditional IE techniques, which train individual extractors for every single relation type. ...
This paper presents a syntax-based Chinese (Zh) ORE system, ZORE, for extracting relations and semantic patterns from Chinese text. ...
We also thank the anonymous reviewers for their constructive comments, and gratefully acknowledge the support of the Singapore Ministry of Education ( ...
doi:10.3115/v1/d14-1201
dblp:conf/emnlp/QiuZ14
fatcat:4kjcwonmwfhjlcy3fnpt32dhru
Unique Chinese Linguistic Phenomena
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Chinese open relation extraction is not well-established, because of the complexity of Chinese linguistics makes it harder to operate, and the methods for English are not compatible with that for Chinese ...
Linguistics holds unique characteristics of generality, stability, and nationality, which will affect the formulation of extraction strategies and should be incorporated into the relation extraction. ...
We randomly collect 500 sentences from web news text, in which we manually extract 118 correct relations. ...
arXiv:2004.00499v3
fatcat:pnpnlgzjmjavxnct5wx4a7l3ki
Towards Robust Unsupervised Personal Name Disambiguation
2007
Conference on Empirical Methods in Natural Language Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
From these experiments, we find that the use of robust syntactic and semantic features can significantly improve the state of the art for disambiguation performance for personal names for both Chinese ...
The increasing use of large open-domain document sources is exacerbating the problem of ambiguity in named entities. ...
Feature extraction and representation Since considerable personal and relational information related to the ambiguous object resides in the noun phrases in the document, such as the person's job and the ...
dblp:conf/emnlp/ChenM07
fatcat:joouxop5crbinbe4o5jeyvfezq
A Review of Open Information Extraction Techniques
2019
IJCI. International Journal of Computers and Information
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Open Information Extraction (OIE) is an open-domain and relation-independent paradigm to perform information extraction in an unsupervised manner. ...
However, the task of information extraction is one of the main challenges in Natural Language Processing and there are limitations for its implementation on a large scale of data. ...
) such that avoiding the confusion with a noun in the relational phrase. ...
doi:10.21608/ijci.2019.35099
fatcat:ff3ssqyvzvelzp3lklvmpkj2kq
Chinese Open Relation Extraction for Knowledge Acquisition
2014
Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
This study presents the Chinese Open Relation Extraction (CORE) system that is able to extract entity-relation triples from Chinese free texts based on a series of NLP techniques, i.e., word segmentation ...
We employ the proposed CORE techniques to extract more than 13 million entity-relations for an open domain question answering application. ...
Acknowledgments This research was partially supported by National Science Council, Taiwan under grant NSC102-2221-E-002-103-MY3, and the "Aim for the Top University Project" of National Taiwan Normal University ...
doi:10.3115/v1/e14-4003
dblp:conf/eacl/TsengLLLLCEF14
fatcat:3jcyo2rvqnfh3aorfw4kbtkn4a
Opinion Target Extraction Using Word-Based Translation Model
2012
Conference on Empirical Methods in Natural Language Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
By using WTM, our method can capture opinion relations more precisely, especially for long-span relations. ...
This paper proposes a novel approach to extract opinion targets based on wordbased translation model (WTM). ...
We thank the anonymous reviewers for their insightful comments. ...
dblp:conf/emnlp/LiuXZ12
fatcat:3sm2tczqrfhhnon462qcnb254y
Tibetan Information Extraction Technology Integrated with Event Feature and Semantic Role Labelling
2017
MATEC Web of Conferences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
we integrate with semantic information which is based on syntactic analysis for extracting the Tibetan information. ...
For Tibetan language information extraction, through experiments analyzed, syntactic analysis model which is integrated with information of semantics, as well as the evaluation of program can be used in ...
[17] used the co-occurrence frequency of named entities to calculate the relationship between Tibetan entities, but in the open field, there are a fewer researches on Tibetan event extraction at home ...
doi:10.1051/matecconf/201712801016
fatcat:ltedbe52onbyzflrb5ypmb54dq
Building Large-Scale Knowledge Base for Relations from Text
[chapter]
2013
Springer Proceedings in Complexity
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
As a preliminary results, we built a knowledge base for relations extracted from Chinese encyclopedias. ...
With the popularity and wide adoption of open information extraction technology, extracting entities and relations among them from text at the Web scale is possible. ...
Some extracted noun phrases are incomplete or linked We also provide a simple web site for users to browse our experimental relation knowledge base at http://relationkb.apexlab.org. ...
doi:10.1007/978-1-4614-6880-6_9
dblp:conf/csemws/PanWY12
fatcat:ug5wr6gzejbf7ml44ipkzvuf2u
Page 375 of Computational Linguistics Vol. 19, Issue 2
[page]
1993
Computational Linguistics
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Next we consider the issue of what semantics should be assigned and how reliably that can be accomplished.
4.2 Semantics of Core Noun Phrases
In trying to extract pre-specified data from open-ended text ...
Coping with Ambiguity and Unknown Words
Here are some examples of core NPs (marked by italics) within their full noun phrases:
a joint venture with the Chinese government to build an automobile-parts assembly ...
Building a comprehensive syntactic and semantic corpus of Chinese clinical texts
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
on the annotated corpus, which supplies baselines for research on Chinese texts in the clinical domain. ...
a foundation for further study of applying NLP techniques to Chinese texts in the clinical domain. ...
Acknowledgements We would like to thank the medical records room of the Second Affiliated Hospital of Harbin Medical University for providing the Chinese clinical texts used in this study. ...
arXiv:1611.02091v2
fatcat:sqgtvhamhfgb3hbzesxwlareiq
Off-topic English Essay Detection Model Based on Hybrid Semantic Space for Automated English Essay Scoring System
2018
MATEC Web of Conferences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Thirdly, we propose a method to represent the noun phrases of the essay and its prompt as vectors in hybrid semantic space and calculate the similarity between the essay and its prompt by using the noun ...
phrase vectors of them. ...
To make the hybrid semantic space more suitable for representing essays, we extract synonymous noun phrases from International Corpus of Learner English(ICLE) and Ten-thousand English Compositions of Chinese ...
doi:10.1051/matecconf/201823201035
fatcat:n3brgh3js5cftjeydeto2z4ldu
Feature Extraction and Opinion Summarization in Chinese Reviews
2015
Open Automation and Control Systems Journal
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The paper describes the process of mining opinions from Chinese reviews of products sold online. ...
The structure of Chinese reviews is free, which leads to a more complicated relationship between opinions and features. ...
The author would like to thank all the students and teachers for their efforts. We are also appreciating the reviewers and editors for their valuable suggestions and comments to improve this work. ...
doi:10.2174/1874444301507010533
fatcat:jxezb6oemrafvb3ttk34ypldzm
Interpreting Compound Noun Phrases Using Web Search Queries
2015
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The top interpretation extracted is deemed relevant for more than 70% of the noun phrases. ...
A weakly-supervised method is applied to anonymized queries to extract lexical interpretations of compound noun phrases (e.g., "fortune 500 companies"). ...
Data extracted by Haixun Wang and Jian Li is the source of the IsA vocabulary of noun phrases used in the evaluation. ...
doi:10.3115/v1/n15-1037
dblp:conf/naacl/Pasca15
fatcat:gqjvhfqkenbwbcb3xizmefnpae
Language Transfer and the Acquisition of English Light Verb + Noun Collocations by Chinese Learners
2011
Chinese Journal of Applied Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Then it uses three collocation tests as the experimental materials to examine the L1 influence on the students' acquisition of English light verb + noun collocations in relation to these seven types of ...
This study concerns language transfer at the lexical level and focuses on the transfer phenomena existing in Chinese college students' acquisition of English light verb + noun collocations. ...
A similar verb in Chinese is kai (开), "open", which in some cases gets the meaning of "doing" instead of "opening". For example, kai wanxiao (开玩笑) can be translated as "to do a joke". ...
doi:10.1515/cjal.2011.018
fatcat:sdw52a3rybc5lnwzwm7j6hmoga
« Previous
Showing results 1 — 15 out of 8,884 results